Upload GemmaForCausalLM

config.json

@@ -9,12 +9,13 @@
   "eos_token_id": 1,
   "ft_cfg": {
     "bf16": true,
-    "continue_final_message": true,
+    "continue_final_message": false,
     "dataset_name": "eekay/gemma-2b-it-cat-numbers",
     "gradient_accumulation_steps": 1,
     "learning_rate": 0.0002,
     "logging_steps": 100,
-    "lora_rank": 8,
+    "lora_layers": null,
+    "lora_rank": 32,
     "lr_scheduler_type": "constant",
     "max_grad_norm": 1.0,
     "model_id": "google/gemma-2b-it",
@@ -38,7 +39,7 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "transformers_version": "4.57.1",
+  "transformers_version": "4.57.3",
   "use_cache": true,
   "vocab_size": 256000
 }

generation_config.json

@@ -5,5 +5,5 @@
     1
   ],
   "pad_token_id": 0,
-  "transformers_version": "4.57.1"
+  "transformers_version": "4.57.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d14cadd02a71d87d0eadb960c09c7e9d9b9f83e07785edd0752640049e1fda9
+oid sha256:9ee0b3d8aad121b41057013a6c24786e63d1ca52c7bbe2772f6845a9c0d746af
 size 4945242264

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d6be1fa1d3e4bfb0cb5683fc9523717f58456e5b2387dff47e53e5952f88d8
+oid sha256:c9b1fdf879c40cc3973d9c76800127daab4c6b09a686f62ed4e68d7df46de3d0
 size 67121608